Configuration

Variables

Advanced Agent applications are composed of independent nodes. Most nodes have input and output items, but the input and output information for each node may not be consistent but dynamic.

How to use a fixed symbol to refer to dynamically changing content? Variables, as dynamic data containers, can store and transmit unfixed content, being referenced mutually within different nodes, providing flexible information mobility between nodes.

System Variables

System variables refer to pre-set system-level parameters within Advanced Agent App that can be globally read by other nodes. All system-level variables begin with sys.

Advanced Agent type application provides the following system variables:

Variables name	Data Type	Description	Remark
sys.query	String	Content entered by the user in the chatting box.
sys.files	Array[File]	File Parameter: Stores images uploaded by users	The image upload function needs to be enabled in the 'Features' section in the upper right corner of the application orchestration page
sys.dialogue_count	Number	The number of conversations turns during the user's interaction with a Advanced Agent application. The count automatically increases by one after each chat round and can be combined with if-else nodes to create rich branching logic. For example, LLM will review the conversation history at the X conversation turn and automatically provide an analysis.
sys.conversation_id	String	A unique ID for the chatting box interaction session, grouping all related messages into the same conversation, ensuring that the LLM continues the chatting on the same topic and context.
sys.user_id	String	A unique ID is assigned for each application user to distinguish different conversation users.

Environment Variables

Environment variables are used to protect sensitive information involved in workflows, such as API keys and database passwords used when running workflows. They are stored in the workflow rather than in the code, allowing them to be shared across different environments.

Supports the following 3 data types:

• String

• Number

• Secret

Environmental variables have the following characteristics:

• Environment variables can be globally referenced within most nodes;

• Environment variable names cannot be duplicated;

• Output variables of nodes are generally read-only and cannot be written to.

---

Conversation Variables

Conversation variables are only applicable to the Advanced Agent App.

Conversation variables allow application developers to specify the particular information that needs to be temporarily stored within the same Advanced Agent session, ensuring that this information can be referenced across multiple rounds of chatting within the current advanced agent. This can include context, files uploaded to the chatting box, user preferences input during the conversation, etc. It's like providing a "memo" for the LLM that can be checked at any time, avoiding information bias caused by LLM memory errors.

For example, you can store the language preference input by the user in the first round of chatting in a conversation variable. The LLM will refer to the information in the conversation variable when answering and use the specified language to reply to the user in subsequent chats.

Conversation variables support the following six data types:

• String

• Number

• Object

• Array[string]

• Array[number]

• Array[object]

Conversation variables have the following features:

• Conversation variables can be referenced globally within most nodes in the same Advanced Agent App;

• Writing to conversation variables requires using the Variable Assigner node;

• Conversation variables are read-write variables;

About how to use conversation variables with the Variable Assigner node, please refer to the Variable Assigner.

Notice

• To avoid variable name duplication, node naming must not be repeated

• The output variables of nodes are generally fixed variables and cannot be edited